{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QEBEAEEO3REGVPIBHYPLFO2IAF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"30b0a154acb06d63ce020614444c91142704b7bc49bd8cac6c7a4b98f9c44cae","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-28T22:31:32Z","title_canon_sha256":"f6412d3f5f7ffe7926e512cde1938846af283ae7f199446e4b36bc88892cc1cb"},"schema_version":"1.0","source":{"id":"2603.00829","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.00829","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"2603.00829v2","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.00829","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"QEBEAEEO3REG","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"pith_short_16","alias_value":"QEBEAEEO3REGVPIB","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"pith_short_8","alias_value":"QEBEAEEO","created_at":"2026-06-02T01:03:44Z"}],"graph_snapshots":[{"event_id":"sha256:bcce57881ed2dcf52f26f3c8b59d9402d99e4ca3aba3bbbebb88e670a9d87ad3","target":"graph","created_at":"2026-06-02T01:03:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.00829/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safe deployment of Large Language Model (LLM) agents in autonomous settings requires reliable oversight mechanisms. A central challenge is detecting scheming, where agents covertly pursue misaligned goals. One approach to mitigating such risks is LLM-based monitoring: using language models to examine agent behaviors for suspicious actions. We study constitutional black-box monitors: prompted classifiers that detect scheming using only externally observable inputs and outputs, optimized on synthetic data generated from natural-language behavior specifications. We introduce two pipelines for gen","authors_text":"James Peters-Gill, Marius Hobbhahn, Rich Barton-Cooper, Simon Storf","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-28T22:31:32Z","title":"Constitutional Black-Box Monitoring for Scheming in LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.00829","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7cdfcff0ef774c66a721380fb7009bf63dc0ca6f454c9e3c2c25595d7b533404","target":"record","created_at":"2026-06-02T01:03:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"30b0a154acb06d63ce020614444c91142704b7bc49bd8cac6c7a4b98f9c44cae","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-28T22:31:32Z","title_canon_sha256":"f6412d3f5f7ffe7926e512cde1938846af283ae7f199446e4b36bc88892cc1cb"},"schema_version":"1.0","source":{"id":"2603.00829","kind":"arxiv","version":2}},"canonical_sha256":"810240108edc486abd013e1eb2bb48014571dbdd3e6a1b128b770e1ee635a1a9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"810240108edc486abd013e1eb2bb48014571dbdd3e6a1b128b770e1ee635a1a9","first_computed_at":"2026-06-02T01:03:44.359417Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:44.359417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"c+B3eMQ5SmsZuyQPrPJkNSZ5ftzxRUCPrim89M+8kVOfxA6WjGZBZ8jb5IURRi+SWJLhWCndgSYZfW4dk1npDw==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:44.359939Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.00829","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7cdfcff0ef774c66a721380fb7009bf63dc0ca6f454c9e3c2c25595d7b533404","sha256:bcce57881ed2dcf52f26f3c8b59d9402d99e4ca3aba3bbbebb88e670a9d87ad3"],"state_sha256":"771bf8c2a9db2c0239bbfffa127028affb9f1354781f2064d3ccd530d398e2e2"}